Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5962
    Prev
    Next
    INDEX
    Explanations

    references to seller policies and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    eBay sellers or listings

    np_acts-logits-general · gemini-2.0-flash

    eBay sellers and listings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.63
     recommandons
    -0.63
     Codable
    -0.61
    Executives
    -0.59
     betweenstory
    -0.59
     collaborateurs
    -0.57
    complexContent
    -0.56
    annica
    -0.55
    Throwable
    -0.55
    InstrumentedTest
    -0.54
    POSITIVE LOGITS
     seller
    1.41
     sellers
    1.26
     listing
    1.25
     Seller
    1.23
     listings
    1.19
     eBay
    1.17
    Seller
    1.12
    seller
    1.11
     Sellers
    1.09
     Listing
    1.05
    Activations Density 0.116%

    No Known Activations